Downloads · 30 days
15
9% of all-time downloads
Qwen2.5-32B-simpo-FP8
radm/Qwen2.5-32B-simpo-FP8
Qwen2.5-32B-simpo-FP8 is a machine learning model from radm. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
All-time downloads
158
Public
Parameters
32.8B
34.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors34.3 GB · 100%
Parameter types
How the weights are stored.
F8_E4M331.2B · 95%
Base models
Model card
From the Hugging Face model README
Model Card for radm/Qwen2.5-32B-simpo-FP8
Model Details
Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
Fine-tuning on A100 in 4-bit with unsloth using SIMPO and custom dataset
LoRA adapter: radm/Qwen2.5-32B-simpo-LoRA
Eval results
Eval results on ZebraLogic
- Type
- qwen2
- Languages
- zho, eng, fra, spa, por, deu
- Created
- Nov 18, 2024
- Updated
- Apr 28, 2025